Short-term forecasting of confirmed daily COVID-19 cases in the Southern African Development Community region

Abstract

Background: The coronavirus pandemic has resulted in complex challenges worldwide, and the Southern African Development Community (SADC) region has not been spared. The region has become the epicentre for coronavirus in the African continent. Combining forecasting techniques can help capture other attributes of the series, thus providing crucial information to address the problem. Objective: To formulate an effective model that timely predicts the spread of COVID-19 in the SADC region. Methods: Using the Quantile regression approaches; linear quantile regression averaging (LQRA), monotone composite quantile regression neural network (MCQRNN), partial additive quantile regression averaging (PAQRA), among others, we combine point forecasts from four candidate models namely, the ARIMA (p, d, q) model, TBATS, Generalized additive model (GAM) and a Gradient Boosting machine (GBM). Results: Among the single forecast models, the GAM provides the best model for predicting the spread of COVID-19 in the SADC region. However, it did not perform well in some periods. Combined forecasts models performed significantly better with the MCQRNN being the best (Theil’s U statistic=0.000000278). Conclusion: The findings present an insightful approach in monitoring the spread of COVID-19 in the SADC region. The spread of COVID-19 can best be predicted using combined forecasts models, particularly the MCQRNN approach. Keywords: Combined Forecasts; LQRA; PLAQR; OPERA; Quantile Regression Neural Networks; COVID-19.